Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quan...
Yunbo Long, Guangya Hao, Yuhan Liu et al.· 0 citations
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations. This source-to-target mapping in these problems carries inherent geometric...
Onur Selim Kilic, Afra Nawar, Cem Okan Yaldiz et al.· 0 citations
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachm...
Zhi-Yuan Qi, Jie-Rui Li, Yi-Fan Shen et al.· 0 citations
Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedba...
Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-agent networks. The observability envelop-the range of what evaluators can reliably infer about an agent's behaviours-is therefore narrowing. Language m...
Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas et al.· 0 citations
Proprietary Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences remains challenging. Existing personalization approaches for black-box LLMs often rely on user-specific scoring heads, causing the number of personali...
We present an AI-assisted Lean 4 formalization of the Poincar\'e conjecture. The project began with limited reusable formal infrastructure for the geometric analysis behind the proof. To organize this work, we combined a proof blueprint prepared by mathematicians with explicit milestone statements. These milestones ena...
Zhiyuan Zhang, Axel Delaval, Leheng Chen et al.· 0 citations
Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric knowledge and costly expert supervision. Self-evolving agents offer a promising alternative by enabling models to improve through iterative task generation...
Xilin Dang, Weilin Ruan, Xue Yang et al.· 0 citations
In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step numeric propositions: a proof is valid only if every content integer is correct, so the pass rate is bounded by the k-th power of the per-integer accuracy...
Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined...
Junkai Liang, Zhanpeng Guo, Pengfei Wu et al.· 0 citations
Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit per...
Shi-Xin Peng, Kun Jiang, Jia-Xing Zheng et al.· 0 citations
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize states or predict outcomes, leaving actions modeled separately through task-specific and often closed label spaces. We introduce Sensor-Language-Action...
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
